Jove
Visualize
Contact Us

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Classification of lung sounds using scalogram representation of sound segments and convolutional neural network.

Journal of medical engineering & technologyยท2022
See all related articles
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jun 5, 2025

Automated Modular High Throughput Exopolysaccharide Screening Platform Coupled with Highly Sensitive Carbohydrate Fingerprint Analysis
12:02

Automated Modular High Throughput Exopolysaccharide Screening Platform Coupled with Highly Sensitive Carbohydrate Fingerprint Analysis

Published on: April 11, 2016

11.4K

Classification of glucose-level in deionized water using machine learning models and data pre-processing technique.

Tri Ngo Quang1,2, Tung Nguyen Thanh1,3, Duc Le Anh1

  • 1International School, Vietnam National University, Hanoi, Vietnam.

Plos One
|December 5, 2024
PubMed
Summary

This study uses Raman spectroscopy and machine learning for non-invasive glucose monitoring, achieving 95% accuracy in classifying glucose levels. Data pre-processing significantly improved model performance for diabetes detection.

More Related Videos

Author Spotlight: Generating Neuronal Phenotypic Profiles - A Protocol to Culture and Image Human Midbrain Dopaminergic Neurons
09:21

Author Spotlight: Generating Neuronal Phenotypic Profiles - A Protocol to Culture and Image Human Midbrain Dopaminergic Neurons

Published on: July 7, 2023

1.4K
Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

488

Related Experiment Videos

Last Updated: Jun 5, 2025

Automated Modular High Throughput Exopolysaccharide Screening Platform Coupled with Highly Sensitive Carbohydrate Fingerprint Analysis
12:02

Automated Modular High Throughput Exopolysaccharide Screening Platform Coupled with Highly Sensitive Carbohydrate Fingerprint Analysis

Published on: April 11, 2016

11.4K
Author Spotlight: Generating Neuronal Phenotypic Profiles - A Protocol to Culture and Image Human Midbrain Dopaminergic Neurons
09:21

Author Spotlight: Generating Neuronal Phenotypic Profiles - A Protocol to Culture and Image Human Midbrain Dopaminergic Neurons

Published on: July 7, 2023

1.4K
Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

488

Area of Science:

  • Biomedical Optics
  • Spectroscopy
  • Machine Learning in Healthcare

Background:

  • Accurate glucose monitoring is crucial for diabetes management.
  • Current methods are invasive and cause discomfort.
  • Non-invasive techniques are needed to improve patient compliance and treatment.

Purpose of the Study:

  • To investigate Raman spectroscopy for non-invasive glucose concentration estimation.
  • To apply machine learning models for classifying glucose levels using spectral data.
  • To evaluate the impact of data pre-processing on model accuracy.

Main Methods:

  • Utilized deionized water samples with known glucose concentrations.
  • Employed Raman spectroscopy to collect spectral data.
  • Applied machine learning models: Extra Trees, Random Forest, and Support Vector Machine (SVM).
  • Implemented data pre-processing: fluorescence background removal and hotspot series extraction.

Main Results:

  • Data pre-processing techniques significantly enhanced classification accuracy.
  • The Extra Trees model achieved the highest accuracy at 95%.
  • Raman spectroscopy combined with machine learning shows promise for glucose level estimation.

Conclusions:

  • Raman spectroscopy is a viable non-invasive method for glucose monitoring.
  • Machine learning models, particularly Extra Trees, can accurately classify glucose levels.
  • Data pre-processing is essential for optimizing the performance of these models.